NVIDIA GPUAI Computing
From professional graphics to data centers, from edge computing to AI inference, NVIDIA's full product portfolio delivers powerful computing power for every industry.
NVIDIA DGX B300
The NVIDIA DGX B300 is an AI infrastructure platform designed for generative AI and large model inference. It features 8 NVIDIA Blackwell Ultra SXM GPUs, delivering up to 144 PFLOPS of FP4 inference performance and 2.1 TB of total GPU memory. Compared to the DGX B200, it offers 1.5× denser FP4 compute performance and 2× faster attention processing. The new 10U chassis supports deployment in NVIDIA MGX racks for the first time, with AC/DC power options and pre-installed NVIDIA AI Enterprise full-stack software—enabling enterprises to run AI workloads at the scale of hyperscale cloud providers.
NVIDIA DGX B200
The NVIDIA DGX B200 is an enterprise-grade unified AI platform powered by 8 NVIDIA Blackwell GPUs connected via fifth-generation NVLink. It delivers 3x training performance and 15x inference performance compared to the previous-generation DGX H100, featuring FP4 compute of 144 PFLOPS (sparse) and a total GPU memory of 1,440GB HBM3e. Designed to support diverse workloads—including large language models, recommendation systems, and chatbots—it serves as the foundational building block for DGX BasePOD and DGX SuperPOD solutions. Preloaded with the NVIDIA AI software stack, it enables end-to-end AI transformation from development to deployment.
NVIDIA RTX PRO 6000 Blackwell Server Edition
The NVIDIA RTX PRO 6000 Blackwell Server Edition is a professional GPU built on the Blackwell architecture for enterprise data centers. It features 96GB of GDDR7 ECC memory and fifth-generation Tensor Cores, delivering up to 4 PFLOPS of FP4 performance and a maximum power draw of 600W (configurable). Available in air-cooled dual-slot and liquid-cooled single-slot form factors, it is optimized for enterprise AI, professional graphics rendering, and data center visualization workloads.
NVIDIA GeForce RTX 5090
Flagship gaming GPU built on Blackwell architecture, featuring 21760 CUDA cores and 32GB of GDDR7 memory, delivering 3352 AI TOPS. Supports DLSS 4 frame generation and full-ray tracing for 4K high-frame-rate gaming and intensive creative workloads.
NVIDIA DGX GB300
The NVIDIA DGX GB300 is a rack-scale liquid-cooled AI system built on the NVIDIA Grace Blackwell Ultra superchip. It integrates 72 Blackwell Ultra GPUs and 36 Grace CPUs, delivering 2,592 Arm Neoverse V2 cores, up to 20TB of GPU memory (with bandwidth up to 576TB/s), and 37TB of total fast memory. With FP4 Tensor Core performance reaching 1440 PFLOPS (sparse), it offers up to 1.5x denser FP4 performance and 2x faster attention mechanisms compared to the DGX GB200. Designed with the NVIDIA MGX chassis, the DGX GB300 can scale to thousands of nodes when combined with DGX SuperPOD. Preloaded with NVIDIA Mission Control and AI Enterprise software, it is optimized for large model training, post-training, and test-time inference.
NVIDIA Jetson AGX Thor T5000
High-performance Jetson modules for humanoid robots, autonomous mobile robots, and industrial edge AI. Featuring Blackwell GPU architecture with 2070 TFLOPS FP4 sparse compute, 128GB LPDDR5X memory, and configurable power from 40 to 130W. Ideal for multi-sensor fusion, real-time inference, and complex robot control.
NVIDIA RTX PRO 5000 Blackwell
The NVIDIA RTX PRO 5000 Blackwell is a professional GPU based on the Blackwell architecture, featuring 48GB of GDDR7 ECC memory (with a 72GB variant available). It includes fifth-generation Tensor Cores and fourth-generation RT Cores, supports FP4 precision and DLSS 4, and features a 300W dual-slot design. Ideal for AI development and inference, data science, 3D rendering, and engineering simulation, it can be deployed in workstations and servers.
NVIDIA GeForce RTX 5080
Blackwell architecture high-end gaming GPU with 10752 CUDA cores, 16GB GDDR7 VRAM, and 1801 AI TOPS for 4K gaming and content creation acceleration.
NVIDIA Jetson AGX Orin 64GB
High-performance module for robotics, intelligent video analytics, and edge AI. Delivers 275 TOPS sparse INT8 compute, 64GB LPDDR5 memory, and configurable power from 15-60W. Ideal for multi-camera setups, SLAM, path planning, and real-time inference.
NVIDIA Vera Rubin NVL72
NVIDIA Vera Rubin NVL72 is a rack-scale agent AI supercomputer that unifies 72 NVIDIA Rubin GPUs, 36 NVIDIA Vera CPUs, NVIDIA ConnectX-9 SuperNICs, and BlueField-4 DPUs on a single platform. It scales vertically via sixth-generation NVLink and NVLink Switch, and horizontally through Quantum-X800 InfiniBand and Spectrum-X Ethernet. Built on the third-generation MGX NVL72 rack design with a cable-free modular tray architecture, it reduces GPU requirements for AI training to one-quarter of Blackwell's and lowers inference costs per million tokens to one-tenth.
NVIDIA GeForce RTX 5070 Ti
Blackwell architecture high-performance GPU with 8960 CUDA cores and 16GB GDDR7 VRAM, delivering 1406 AI TOPS for 2K and 4K high-frame-rate gaming.
NVIDIA RTX PRO 4500 Blackwell Server Edition
NVIDIA RTX PRO 4500 Blackwell Server Edition is a single-slot, passive-cooled professional GPU built on the Blackwell architecture, featuring 32GB GDDR7 memory, 165W power consumption, 1.6 FP4 performance in PFLOPS, and support for up to 2 MIG instances. Ideal for enterprise AI inference, visual computing, and high-density data center deployments.
NVIDIA Jetson AGX Orin 32GB
Delivers 241 TOPS sparse INT8 compute and 32GB LPDDR5 memory with compact power consumption, ideal for industrial inspection, mobile robots, and smart retail terminals.
NVIDIA GeForce RTX 5070
Blackwell architecture mainstream high-end GPU with 6144 CUDA cores and 12GB GDDR7 VRAM, delivering 988 AI TOPS for 2K and entry-level 4K gaming.
NVIDIA Jetson AGX Orin Industrial
Industrial-grade AGX Orin variant delivers 248 TOPS sparse INT8 AI performance, 64GB ECC LPDDR5 memory, 15-75W power consumption with wide-temperature operation. Ideal for factory automation, outdoor devices, and long-term supply scenarios.
NVIDIA RTX PRO 6000 Blackwell Workstation Edition
Blackwell flagship professional workstation GPU with 96GB GDDR7 ECC memory and 1792GB/s bandwidth, delivering 4000 AI TOPS (FP4 sparsity) for large model local inference, complex simulations, and film-grade rendering.
NVIDIA Jetson Orin NX 16GB
Compact edge AI module with Super mode delivering 157 TOPS sparse INT8 performance and standard mode offering 100 TOPS. Equipped with 16GB LPDDR5 memory and configurable power ranging from 10-25W. Ideal for drones, mobile robots, and smart cameras.
NVIDIA GeForce RTX 5060 Ti
Blackwell architecture GPU with exceptional value: 4608 CUDA cores, 16GB or 8GB GDDR7 VRAM, 759 AI TOPS. Designed for 4K and 2K gaming.
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
The low-power Max-Q version of the RTX PRO 6000 features the same 96GB GDDR7 ECC memory, 3511 AI TOPS, and 300W power consumption—ideal for professional workstations with space and thermal constraints.
NVIDIA RTX PRO 5500 Blackwell Workstation Edition
Blackwell professional workstation GPU with 84GB GDDR7 ECC memory and 1398GB/s bandwidth, designed for big data sets, rendering, and simulation workloads.
NVIDIA GeForce RTX 5060
Blackwell architecture mainstream GPU with 3840 CUDA cores and 8GB GDDR7 VRAM, delivering 614 AI TOPS for 1080p gaming and everyday content creation.
NVIDIA Jetson Orin NX 8GB
Compact edge AI module. Super mode delivers 117 TOPS sparse INT8 performance; standard mode offers 70 TOPS. Equipped with 8GB LPDDR5 memory and configurable power from 10 to 25W, ideal for cost- and power-sensitive edge vision devices.
NVIDIA RTX PRO 4500 Blackwell Workstation Edition
Blackwell professional workstation mainstream GPU with 32GB GDDR7 ECC memory, 200W power consumption. Designed for professional design, engineering simulation, and video production.
NVIDIA GeForce RTX 5050
Entry-level Blackwell architecture GPU with 2560 CUDA cores and 8GB GDDR6 VRAM, delivering 421 AI TOPS for entry-level RTX gaming and light creative work.
NVIDIA Jetson Orin Nano 8GB (Super)
Entry-level edge AI module with Super mode delivering 67 TOPS sparse INT8 compute and Raw mode providing 40 TOPS. Features 8GB LPDDR5 memory and configurable power consumption from 7 to 25W, ideal for robotics, edge vision, and AI development.
NVIDIA GB300 NVL72
The NVIDIA GB300 NVL72 features a full liquid-cooled rack-scale architecture that integrates 72 NVIDIA Blackwell Ultra GPUs and 36 Arm-based NVIDIA Grace CPUs onto a single platform. Compared to Blackwell GPUs, it delivers up to 1.5× more dense FP4 Tensor Core performance and up to 2× better attention mechanism performance, purpose-built for test-time scaling inference and AI inference workloads. Paired with Quantum-X800 InfiniBand or Spectrum-X Ethernet, ConnectX-8 SuperNICs, and NVIDIA Mission Control management, the entire AI factory achieves up to 50× higher throughput than Hopper-based platforms.
NVIDIA RTX PRO 4000 Blackwell
Blackwell single-slot professional GPU with 24GB GDDR7 ECC memory, 1290 AI TOPS, and 145W power consumption—ideal for compact professional workstations.
NVIDIA GeForce RTX 4090
Flagship Ada Lovelace GPU with 16384 CUDA cores, 24GB GDDR6X VRAM, 1321 AI TOPS, and DLSS 3 support. Built for 4K gaming and professional creation.
NVIDIA Jetson Orin Nano 4GB (Super)
A lightweight edge AI module. Super mode delivers 34 TOPS sparse INT8 compute; native mode offers 20 TOPS. Equipped with 4GB LPDDR5 memory and configurable power consumption from 7 to 2-5W. Ideal for smart cameras, edge inference, and prototyping.
NVIDIA GB200 NVL72
The NVIDIA GB200 NVL72 uses rack-scale liquid cooling to connect 36 Grace CPUs and 72 Blackwell GPUs. Its 72-GPU NVLink domain operates as a single large GPU, delivering 130TB/s ultra-low latency interconnects. Compared to the H100 platform, it accelerates real-time inference for trillion-parameter LLMs by 30x, LLM training by 4x, energy efficiency by 25x, and database query processing by 18x over CPUs. The GB200 Grace Blackwell superchip is the system's core building block, linking two Blackwell Tensor Core GPUs with one Grace CPU via NVLink-C2C.
NVIDIA RTX PRO 4000 Blackwell SFF Edition
Blackwell professional GPU for small form factor (SFF) systems, 24GB GDDR7 ECC memory, 70W low power consumption, 770 AI TOPS.
NVIDIA Jetson AGX Xavier 32GB
The previous-generation high-performance edge AI module delivers 32 TOPS of compute power, 32GB LPDDR4x memory, and configurable power consumption ranging from 10 to 30W. Ideal for upgrading existing industrial equipment and maintaining long-term projects.
NVIDIA GeForce RTX 4080 SUPER
Ada Lovelace high-end GPU with 10240 CUDA cores, 16GB GDDR6X VRAM, and 836 AI TOPS for 4K gaming and creation.
NVIDIA H200
The NVIDIA H200 is a memory-enhanced data center GPU based on the H100, featuring 141GB of HBM3e memory and 4.8 TB/s bandwidth. It delivers significantly higher throughput and lower latency for large language model inference. Available in SXM and NVL form factors, it supports generative AI training and inference, as well as high-performance computing (HPC) workloads.
NVIDIA GeForce RTX 4070 Ti SUPER
High-end Ada Lovelace GPU with 8448 CUDA cores, 16GB GDDR6X VRAM, and 706 AI TOPS for 2K high-framerate and entry-level 4K gaming.
NVIDIA Jetson Xavier NX 16GB
Compact edge AI module delivering 21 TOPS of compute, 16GB LPDDR4x memory, and configurable power consumption from 10 to 20W. Ideal for space-constrained industrial cameras, robots, and edge gateways.
NVIDIA RTX PRO 2000 Blackwell
Blackwell Entry-Level Professional GPU: 16GB GDDR7 ECC VRAM, 70W TDP, 545 AI TOPS. Optimized for CAD, DCC, and lightweight AI workloads.
NVIDIA H100
The NVIDIA H100 is a data center GPU based on the Hopper architecture, available in SXM, PCIe, and H100 NVL form factors. It features up to 80 GB of HBM3 memory (with 4 GB per card for the NVL version), offers fourth-generation NVLink bandwidth of 900 GB/s, supports Multi-Instance GPU (MIG), and serves as a leading compute platform for large model training, HPC, and large-scale inference.
NVIDIA Jetson Xavier NX 8GB
Compact edge AI module delivering 21 TOPS of compute power, 8GB LPDDR4x memory, and configurable power consumption from 10-20W. Ideal for low-power edge vision and embedded AI terminals.
NVIDIA GeForce RTX 4070 SUPER
Mainstream high-end graphics card featuring Ada Lovelace architecture, 7168 CUDA cores with 12GB GDDR6X VRAM, 568 AI TOPS. Designed for 2K gaming and creation.
NVIDIA GeForce RTX 4070
Mainstream Ada Lovelace GPU with 5888 CUDA cores, 12GB GDDR6 memory, and 466 AI TOPS. Built for 2K gaming and everyday creation.
NVIDIA Jetson TX2
Classic embedded AI module delivering 1.33 TFLOPS of compute power, 8GB LPDDR4 memory, and configurable power consumption from 7.5 to 15W. Ideal for industrial vision, robotics, and legacy edge computing projects.
NVIDIA GH200 Grace Hopper Superchip
The NVIDIA GH200 Grace Hopper Superchip connects the 72-core Arm Grace CPU and Hopper GPU via a unified memory architecture through NVLink-C2C (900 GB/s). It is available with 96GB or 144GB of HBM3/HBM3e memory, with up to 480GB of total CPU memory LPDDR5X, making it ideal for large model training and inference, high-performance computing (HPC), and recommendation systems.
NVIDIA GeForce RTX 4060 Ti
High-value Ada Lovelace GPU with 4352 CUDA cores, 16GB or 8GB GDDR6 VRAM, 353 AI TOPS, optimized for 1080p and 2K gaming.
NVIDIA Jetson TX2i
Industrial-grade TX2 module delivering 1.26 TFLOPS of compute power, 8GB ECC LPDDR4 memory, 10-20W power consumption, and operating temperatures from -25°C to 80°C—built for harsh industrial environments.
NVIDIA L40S
The NVIDIA L40S is a general-purpose data center GPU based on the Ada Lovelace architecture, featuring 48GB GDDR6 ECC memory. It combines third-generation RT Cores and fourth-generation Tensor Cores to support generative AI fine-tuning and inference, graphics rendering, and video processing. It comes in a 350W dual-slot PCIe form factor.
NVIDIA Jetson TX2 4GB
Entry-level TX2 module delivering 1.33 TFLOPS of compute, 4GB LPDDR4 memory, and configurable power from 7.5-15W. Ideal for lightweight visual inference and device upgrades.
NVIDIA GeForce RTX 4060
Entry-level Ada Lovelace graphics card with 3072 CUDA cores, 8GB GDDR6 memory, 242 AI TOPS, designed for 1080p gaming.
NVIDIA L40
NVIDIA L40 is a data center GPU based on the Ada Lovelace architecture, designed for professional graphics and AI workloads. It features 48GB GDDR6 ECC memory, third-generation RT Cores, and is ideal for AI image generation, ray tracing rendering, virtual workstations, and video processing. The card has a 300W dual-slot PCIe form factor.
NVIDIA L4
The NVIDIA L4 is a lightweight data center GPU based on the Ada Lovelace architecture. It features a 72W single-slot low-profile design and 24GB GDDR6 memory, with hardware AV1 encoding and decoding support. Ideal for video transcoding, lightweight AI inference, cloud gaming, and virtual desktops, it delivers exceptional performance per watt and high deployment density.
NVIDIA Jetson Nano 4GB
Entry-level edge AI module delivering 472 GFLOPS / 0.5 TFLOPS of compute, 4GB LPDDR4 memory, and configurable power consumption from 5 to 10W. Ideal for smart cameras, educational development, lightweight inference, and maintenance of existing A02/B01 projects.
NVIDIA RTX Spark N1X
Blackwell RTX superchip for slim laptops and compact desktops: 6144-core GPU, 20-core Grace CPU, up to 128GB unified memory, AI performance up to 1 PFLOPS (FP4), sold via OEM systems.
NVIDIA A100 80GB
The NVIDIA A100 80GB is a flagship Ampere-based training GPU featuring 80GB HBM2e memory, third-generation Tensor Cores, and Multi-Instance GPU (MIG) technology. Available in both SXM and PCIe form factors, it serves as the go-to compute platform for large-scale model training, fine-tuning, and HPC. In the domestic market, the A800 variant offers NVLink bandwidth adjusted to 400 GB/s.
NVIDIA A40
The NVIDIA A40 is a data center GPU based on the Ampere architecture, combining professional graphics rendering with AI computing power. It features 48GB GDDR6 ECC memory, second-generation RT Cores, and third-generation Tensor Cores, supports dual-card NVLink bridging, and is ideal for graphics rendering, virtual workstations (vGPU), and AI inference.
NVIDIA A30
The NVIDIA A30 is a mainstream compute GPU based on the Ampere architecture, featuring 24GB HBM2e memory and 933 GB/s bandwidth. It supports MIG (up to 4 instances) and FP64 double-precision computing, making it ideal for AI inference, model fine-tuning, and database acceleration.
NVIDIA A16
NVIDIA A16 integrates 4 Ampere architecture GPUs (4x 16GB GDDR6, totaling 64GB) in a dual-slot, 250W form factor. It features multi-channel NVENC/NVDEC codecs and is purpose-built for high-density virtual desktop infrastructure (VDI) and multi-user virtual workstations (vGPU).
NVIDIA A10
The NVIDIA A10 is a single-slot data center GPU based on the Ampere architecture, featuring 24GB of GDDR6 memory and a 150W TDP. It delivers balanced performance for AI inference, cloud gaming, virtual workstations, and video processing; the A10G is a variant customized for cloud service providers.
NVIDIA A2
The NVIDIA A2 is an entry-level data center GPU based on the Ampere architecture, featuring 16GB of GDDR6 memory. Its low-profile, single-slot, low-power design makes it ideal for entry-level AI inference, video transcoding, and virtual desktops, enabling easy large-scale deployment in standard servers.
NVIDIA DGX Spark
Desktop AI supercomputer powered by the GB10 Grace Blackwell superchip, featuring a 20-core Grace CPU and Blackwell GPU with coherent unified 12 8GB memory. Delivers up to 1 PFLOPS of FP4 AI performance, supporting local development and inference for large-parameter models, with scalability up to 4 nodes in a cluster.
Need NVIDIA solutions?
As an NVIDIA partner, Huaying Technology provides end-to-end professional services—from selection consulting to deployment implementation.